Jerome Herath
Principle AI Engineer at Spacewalk AI
United States
Summary
👤
Senior🎓
Top SchoolJerome Herath is a Principal AI Engineer with nine years of experience applying machine learning and deep learning to cybersecurity, currently building AI-powered incident response at Spacewalk AI. He holds a PhD from Binghamton University where his dissertation and projects advanced explainable and adversarial ML for malware classification, real-time anomaly detection, and tamper-proof scientific workflows. At Obsidian Security he helped deliver a governed multi-agent AI assistant and end-to-end evaluation and tracing systems that accelerate SaaS threat investigations and analyst workflows. Jerome’s background spans time-series forecasting, graph neural networks, Markovian models and blockchain-backed data integrity, reflecting a rare mix of research depth and production-focused engineering. He combines hands-on model building with security-first product thinking and a track record of turning novel research (e.g., CFGExplainer, RAMP, SciBlock) into operational tooling.
9 years of coding experience
8 years of employment as a software developer
Ordinary Level Advanced Level Assistant Head Prefect, Ordinary Level Advanced Level Assistant Head Prefect at St. Josephs College, Colombo 10, Sri LankaDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Binghamton UniversityBachelor of Science - BS Computational Physics, Bachelor of Science - BS Computational Physics at University of ColomboProfessional Postgraduate Diploma in Marketing Marketing, Professional Postgraduate Diploma in Marketing Marketing at CIM | The Chartered Institute of Marketing
Sinhalese, English
Github Skills (14)
graph-neural-network10
classification10
control-flow-graph10
malware9
3d6
wireless4
opengl4
time-series-forecasting2
deep-learning2
sustainability1
machine-learning1
python1
parsing1
garbage-collection1
Programming languages (4)
Github contributions (5)
dherath/CFGExplainer
Jun 2021 - Aug 2022
[code] "CFGExplainer: Explaining Graph Neural Network-Based Malware Classification from Control Flow Graphs" by Jerome Dinal Herath, Priti Prabhakar Wakodikar, Ping Yang and Guanhua Yan. In: IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) (2022)
Contributions:31 commits, 4 pushes, 1 comment in 1 year 1 month
classificationcontrol-flow-graphgraph-neural-networkmalware
dherath/udacityCourses
Apr 2017 - Sep 2019
Contributions:141 pushes, 1 branch in 2 years 5 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.